rpryzant / deconfounded-lexicon-inductionLinks
Find text features that are most related to an outcome, controlling for confounds.
☆60Updated last year
Alternatives and similar repositories for deconfounded-lexicon-induction
Users that are interested in deconfounded-lexicon-induction are comparing it to the libraries listed below
Sorting:
- Software and data for "Using Text Embeddings for Causal Inference"☆125Updated 4 years ago
- Learning the Difference that Makes a Difference with Counterfactually-Augmented Data☆170Updated 4 years ago
- ☆54Updated 3 years ago
- Training Temporal Word Embeddings with a Compass☆64Updated 2 years ago
- Package for computing causal effects of text (as treatment)☆70Updated 3 years ago
- Materials for the EMNLP 2020 Tutorial on "Interpreting Predictions of NLP Models"☆199Updated 4 years ago
- Tutorial on computational models of language change☆115Updated 6 years ago
- Skip-gram word embeddings in hyperbolic space☆34Updated 6 years ago
- Tensorflow 2 implementation of Causal-BERT☆71Updated last year
- ☆136Updated 4 years ago
- CausalNLP is a practical toolkit for causal inference with text as treatment, outcome, or "controlled-for" variable.☆151Updated 6 months ago
- Interpretable Neural Predictions with Differentiable Binary Variables☆84Updated 4 years ago
- Pytorch implementation of "Adapting Text Embeddings for Causal Inference"☆92Updated 3 years ago
- Text classification models. Used a submodule for other projects.☆68Updated 6 years ago
- Learned string similarity for entity names using optimal transport.☆35Updated 4 years ago
- Code for the paper "Analyzing Polarization in Social Media: Method and Application to Tweets on 21 Mass Shootings"☆69Updated 2 years ago
- Learning Gender-Neutral Word Embeddings☆47Updated 5 years ago
- Hyperparameter Search for AllenNLP☆139Updated 5 months ago
- ☆53Updated last year
- Source code for "Towards Hierarchical Importance Attribution: Explaining Compositional Semantics for Neural Sequence Models", ICLR 2020.☆30Updated 5 years ago
- Dataset and code of our EMNLP 2019 paper "Multilingual and Multi-Aspect Hate Speech Analysis"☆57Updated 8 months ago
- ☆87Updated 3 years ago
- diagNNose is a Python library that facilitates a broad set of tools for analysing hidden activations of neural models.☆82Updated last year
- ☆53Updated 5 years ago
- [NAACL 2021] This is the code for our paper `Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self…☆203Updated 2 years ago
- Collection of NLP model explanations and accompanying analysis tools☆144Updated 2 years ago
- This repository contains the code for "BERTRAM: Improved Word Embeddings Have Big Impact on Contextualized Representations".☆64Updated 4 years ago
- ☆27Updated 2 years ago
- A list of publications on NLP interpretability (Welcome PR)☆168Updated 4 years ago
- Code for "Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?"☆45Updated last year